Z Lab

Popular repositories Loading

1. dflash dflash Public

   DFlash: Block Diffusion for Flash Speculative Decoding

   Python 5.8k 412

2. paroquant paroquant Public

   [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

   Python 331 33

3. sparselora sparselora Public

   [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

   Python 78 7

4. flashdrive flashdrive Public

   Flash Vision-Language-Action Inference for Autonomous Driving

   Python 64 7

5. flash-colreduce flash-colreduce Public

   Fast, memory-efficient attention column reduction (e.g., sum, mean, max)

   Python 51 3

6. omlx-fork omlx-fork Public

   Forked from jundot/omlx

   LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

   Python 1 1